© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 61172
    Prev
    Next
    INDEX
    Explanations

    São Paulo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sWith
    -0.10
    arian
    -0.09
    è¿ŀäºij
    -0.09
    åĮħåĮħ
    -0.09
    CTS
    -0.09
    åĸĩåıŃ
    -0.09
    -expand
    -0.09
    ewire
    -0.09
    éĽ²
    -0.09
    eer
    -0.09
    POSITIVE LOGITS
    0.11
     dioxide
    0.08
    posite
    0.08
    æĹĹä¸ĭ
    0.08
    itra
    0.08
    amiento
    0.08
    obi
    0.08
    illard
    0.08
    客
    0.08
    -eyed
    0.07
    Activations Density 0.005%

    No Known Activations